BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220812T074334Z
LOCATION:Boston 3 Room
DTSTART;TZID=Europe/Stockholm:20220627T163000
DTEND;TZID=Europe/Stockholm:20220627T170000
UID:submissions.pasc-conference.org_PASC22_sess138_msa109@linklings.com
SUMMARY:Probabilistic Physics-Based Machine Learning for Digital Twinning 
 Enabled by Bridging Supercomputing and Real-Time Computing
DESCRIPTION:Minisymposium\n\nProbabilistic Physics-Based Machine Learning 
 for Digital Twinning Enabled by Bridging Supercomputing and Real-Time Comp
 uting\n\nFarhat, Azzi\n\nThis lecture will focus on the construction of a 
 digital twin instance (DTI) – that is, a DT of an individual instance of a
  product <em>after</em> it has been manufactured and equipped with sensors
  that provide vital information during its deployment. It can serve many p
 urposes, including: enabling a predictive rather than scheduled maintenanc
 e; performing reliable structural health monitoring; enabling model predic
 tive control; and enabling operation at performance limits. Specifically, 
 the lecture will present a feasible probabilistic framework for enriching 
 a computational model with sensor data to reduce its model-form uncertaint
 y; and continuously update it to enhance its predictive ability. The frame
 work is grounded in a physics-based, machine learning approach for extract
 ing from sensor data information that is not captured by a deterministic c
 omputational model and infusing it into a lower dimensional stochastic cou
 nterpart constructed using a randomized, projection-based model order redu
 ction method enabled by supercomputing. As a benefit, the stochastic, proj
 ection-based reduced-order model delivers near-real-time numerical predict
 ions in the form of confidence intervals that contain the true values of t
 he quantities of interest, within a specified confidence level. The lectur
 e will demonstrate the framework with applications pertaining to car crash
  analysis and model predictive control of autonomous aircraft landing.\n\n
 Domain: Chemistry and Materials, Computer Science and Applied Mathematics,
  Engineering
END:VEVENT
END:VCALENDAR